1
0
mirror of https://github.com/MariaDB/server.git synced 2025-07-29 05:21:33 +03:00

MDEV-5363: Make parallel replication waits killable

Add a test case for killing a waiting query in parallel replication.

Fix several bugs found:

 - We should not wakeup_subsequent_commits() in ha_rollback_trans(), since we
   do not know the right wakeup_error() to give.

 - When a wait_for_prior_commit() is killed, we must unregister from the
   waitee so we do not race and get an extra (non-kill) wakeup.

 - We need to deal with error propagation correctly in queue_for_group_commit
   when one thread is killed.

 - Fix one locking issue in queue_for_group_commit(), we could unlock the
   waitee lock too early and this end up processing wakeup() with insufficient
   locking.

 - Fix Xid_log_event::do_apply_event; if commit fails it must not update the
   in-memory @@gtid_slave_pos state.

 - Fix and cleanup some things in the rpl_parallel.cc error handling.

 - Add a missing check for killed in the slave sql driver thread, to avoid a
   race.
This commit is contained in:
unknown
2013-12-13 14:26:51 +01:00
parent b7ae65ef86
commit dbfe5f4774
9 changed files with 367 additions and 74 deletions

View File

@ -19,6 +19,7 @@ CHANGE MASTER TO master_use_gtid=slave_pos;
--echo *** Test long-running query in domain 1 can run in parallel with short queries in domain 0 ***
--connection server_1
ALTER TABLE mysql.gtid_slave_pos ENGINE=InnoDB;
CREATE TABLE t1 (a int PRIMARY KEY) ENGINE=MyISAM;
CREATE TABLE t2 (a int PRIMARY KEY) ENGINE=InnoDB;
INSERT INTO t1 VALUES (1);
@ -333,6 +334,126 @@ SELECT * FROM t2 WHERE a >= 20 ORDER BY a;
SELECT * FROM t3 WHERE a >= 20 ORDER BY a;
--connection server_2
# Respawn all worker threads to clear any left-over debug_sync or other stuff.
--source include/stop_slave.inc
SET GLOBAL binlog_format=@old_format;
SET GLOBAL slave_parallel_threads=0;
SET GLOBAL slave_parallel_threads=10;
--source include/start_slave.inc
--echo *** Test killing slave threads at various wait points ***
--echo *** 1. Test killing transaction waiting in commit for previous transaction to commit ***
# Set up three transactions on the master that will be group-committed
# together so they can be replicated in parallel on the slave.
--connection con_temp3
SET debug_sync='commit_after_release_LOCK_prepare_ordered SIGNAL master_queued1 WAIT_FOR master_cont1';
SET binlog_format=statement;
send INSERT INTO t3 VALUES (31, foo(31,
'commit_before_prepare_ordered WAIT_FOR t2_waiting',
'commit_after_prepare_ordered SIGNAL t1_ready WAIT_FOR t1_cont'));
--connection server_1
SET debug_sync='now WAIT_FOR master_queued1';
--connection con_temp4
SET debug_sync='commit_after_release_LOCK_prepare_ordered SIGNAL master_queued2';
SET binlog_format=statement;
BEGIN;
# This insert is just so we can get T2 to wait while a query is running that we
# can see in SHOW PROCESSLIST so we can get its thread_id to kill later.
INSERT INTO t3 VALUES (32, foo(32,
'ha_write_row_end SIGNAL t2_query WAIT_FOR t2_cont',
''));
# This insert sets up debug_sync points so that T2 will tell when it is at its
# wait point where we want to kill it - and when it has been killed.
INSERT INTO t3 VALUES (33, foo(33,
'group_commit_waiting_for_prior SIGNAL t2_waiting',
'group_commit_waiting_for_prior_killed SIGNAL t2_killed'));
send COMMIT;
--connection server_1
SET debug_sync='now WAIT_FOR master_queued2';
--connection con_temp5
SET debug_sync='commit_after_release_LOCK_prepare_ordered SIGNAL master_queued3';
SET binlog_format=statement;
send INSERT INTO t3 VALUES (34, foo(34,
'',
''));
--connection server_1
SET debug_sync='now WAIT_FOR master_queued3';
SET debug_sync='now SIGNAL master_cont1';
--connection con_temp3
REAP;
--connection con_temp4
REAP;
--connection con_temp5
REAP;
--connection server_1
SELECT * FROM t3 WHERE a >= 30 ORDER BY a;
--connection server_2
SET sql_log_bin=0;
CALL mtr.add_suppression("Query execution was interrupted");
CALL mtr.add_suppression("Commit failed due to failure of an earlier commit on which this one depends");
SET sql_log_bin=1;
# Wait until T2 is inside executing its insert of 32, then find it in SHOW
# PROCESSLIST to know its thread id for KILL later.
SET debug_sync='now WAIT_FOR t2_query';
--let $thd_id= `SELECT ID FROM INFORMATION_SCHEMA.PROCESSLIST WHERE INFO LIKE '%foo(32%' AND INFO NOT LIKE '%LIKE%'`
SET debug_sync='now SIGNAL t2_cont';
# Wait until T2 has entered its wait for T1 to commit, and T1 has
# progressed into its commit phase.
SET debug_sync='now WAIT_FOR t1_ready';
# Now kill the transaction T2.
--replace_result $thd_id THD_ID
eval KILL $thd_id;
# Wait until T2 has reacted on the kill.
SET debug_sync='now WAIT_FOR t2_killed';
# Now we can allow T1 to proceed.
SET debug_sync='now SIGNAL t1_cont';
--let $slave_sql_errno= 1317,1963
--source include/wait_for_slave_sql_error.inc
STOP SLAVE IO_THREAD;
SELECT * FROM t3 WHERE a >= 30 ORDER BY a;
# Now we have to disable the debug_sync statements, so they do not trigger
# when the events are retried.
SET GLOBAL slave_parallel_threads=0;
SET GLOBAL slave_parallel_threads=10;
SET sql_log_bin=0;
DROP FUNCTION foo;
--delimiter ||
CREATE FUNCTION foo(x INT, d1 VARCHAR(500), d2 VARCHAR(500))
RETURNS INT DETERMINISTIC
BEGIN
RETURN x;
END
||
--delimiter ;
SET sql_log_bin=1;
--connection server_1
INSERT INTO t3 VALUES (39,0);
--save_master_pos
--connection server_2
--source include/start_slave.inc
--sync_with_master
SELECT * FROM t3 WHERE a >= 30 ORDER BY a;
--connection server_2
--source include/stop_slave.inc
SET GLOBAL binlog_format=@old_format;